© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10785
    Prev
    Next
    INDEX
    Explanations

    Danger/safely context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moot
    -0.08
    èĩªåĬ¨æĶ¾å¼ĥ
    -0.07
     insign
    -0.07
    _abstract
    -0.07
    orst
    -0.07
    å¾®ä¸į足éģĵ
    -0.07
    ç¡®å®ļæĢ§
    -0.06
    asc
    -0.06
    æĥ¦
    -0.06
     dì
    -0.06
    POSITIVE LOGITS
     dangerously
    0.15
    åį±éĻ©çļĦ
    0.14
    Danger
    0.13
    danger
    0.13
    åį±éĻ©
    0.13
     dangerous
    0.13
    åį±éĻº
    0.12
     safely
    0.12
     Dangerous
    0.12
     Danger
    0.12
    Activations Density 0.955%

    No Known Activations